LLM Digest

Story

arxiv_cs_ai · Nov 3, 2026 · paper

Source brief

HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation

arxiv.orgNov 3, 2026
original source linked

In brief

In LLM-based recommendation, memory acts as a user-level agent in a memory-augmented backbone. Yet users and items remain asymmetric: only the user is given a structured profile; it enters a bandwidth-limited reranker...

Feed lens

agenticeval

Read the original at arxiv.org →Open in live feed Read that day’s brief

HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation

Earlier in this thread 4 items

Trajectory Unlearning on LLM-based Agents

What Does the Model See? Representation Validity in Multimodal LLM-Based Video Analysis

Coarse Semantic Blocks for Efficient Training-Free Sparse Attention

RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models